Serverless

DeepInfra

Pay-as-you-go inference for 100+ open and proprietary models, plus GPUs

Fireworks AI

Serverless inference, GPU deployments and fine-tuning for open models

Inngest

Durable execution for backend and AI workflows, no queues to run.

LanceDB

Embedded multimodal retrieval on the Lance format, with an enterprise lakehouse

Modal

Serverless GPUs, sandboxes and inference, driven from Python

Parasail

Open-model inference: serverless per token, dedicated per GPU-hour

Pinecone

Serverless vector database with pay-per-use pricing

turbopuffer

Serverless vector and full-text search on object storage, cheap when cold